© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16453
    Prev
    Next
    INDEX
    Explanations

    phrases related to email or mailing instructions

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation "MA" associated with listings or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pwr
    -0.74
     Fired
    -0.71
    naires
    -0.68
    auts
    -0.63
    lings
    -0.62
     Ange
    -0.60
    lists
    -0.59
     Ceres
    -0.58
    naire
    -0.58
    mask
    -0.58
    POSITIVE LOGITS
    KING
    1.38
    KER
    1.36
    IL
    1.13
    ZE
    1.10
    KE
    1.09
    ILY
    1.03
    VEN
    1.02
    INT
    1.00
    uthor
    0.96
    ILA
    0.95
    Activations Density 0.015%

    No Known Activations